Optimized PV Panel Control in Hybrid DC Microgrid Systems Using Whale Optimization & Reinforcement Learning

As the demand for reliable and sustainable energy grows, DC microgrids powered by renewable sources are becoming an efficient alternative for modern power systems. This research introduces an optimized control strategy for a DC microgrid that combines solar, wind, and batteries, ensuring efficient power management and uninterrupted energy supply to connected loads. The system leverages the Whale Optimization Algorithm combined with Reinforcement Learning to enhance Maximum Power Point Tracking for solar panels, enabling real-time adaptation to changing environmental conditions. A dedicated power converter controls the DC bus voltage, and the battery circuit maximizes charging and discharging to maintain system stability. Additionally, a power flow management algorithm is developed to ensure optimal energy distribution among the three sources. The proposed approach is implemented and tested in SIMULINK under varying solar and wind conditions. Simulation results demonstrate improved energy harvesting, faster convergence, enhanced voltage regulation, and higher system efficiency. This research contributes to the advancement of smart and self-sustaining DC microgrids, providing an intelligent solution for renewable energy management.